Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix(color-contrast): ignore format unicode characters #4102

Merged
merged 4 commits into from
Jul 26, 2023
Merged

fix(color-contrast): ignore format unicode characters #4102

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
fff54e8
fix(color-contrast): ignore format unicode characters
straker Jul 24, 2023
fa138e7
comment
straker Jul 24, 2023
a4a8e52
typo
straker Jul 24, 2023
564a89f
Apply suggestions from code review
straker Jul 26, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
18 changes: 11 additions & 7 deletions lib/commons/text/has-unicode.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
import {
getUnicodeNonBmpRegExp,
getSupplementaryPrivateUseRegExp,
getPunctuationRegExp
getPunctuationRegExp,
getCategoryFormatRegExp
} from './unicode';
import emojiRegexText from 'emoji-regex';

Expand All @@ -20,19 +21,22 @@ import emojiRegexText from 'emoji-regex';
*/
function hasUnicode(str, options) {
const { emoji, nonBmp, punctuations } = options;
let value = false;

if (emoji) {
return emojiRegexText().test(str);
value ||= emojiRegexText().test(str);
}
if (nonBmp) {
return (
value ||=
getUnicodeNonBmpRegExp().test(str) ||
getSupplementaryPrivateUseRegExp().test(str)
);
getSupplementaryPrivateUseRegExp().test(str) ||
getCategoryFormatRegExp().test(str);
}
if (punctuations) {
return getPunctuationRegExp().test(str);
value ||= getPunctuationRegExp().test(str);
}
return false;

return value;
}

export default hasUnicode;
9 changes: 6 additions & 3 deletions lib/commons/text/remove-unicode.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
import {
getUnicodeNonBmpRegExp,
getSupplementaryPrivateUseRegExp,
getPunctuationRegExp
getPunctuationRegExp,
getCategoryFormatRegExp
} from './unicode.js';
import emojiRegexText from 'emoji-regex';

Expand All @@ -25,8 +26,10 @@ function removeUnicode(str, options) {
str = str.replace(emojiRegexText(), '');
}
if (nonBmp) {
str = str.replace(getUnicodeNonBmpRegExp(), '');
str = str.replace(getSupplementaryPrivateUseRegExp(), '');
str = str
.replace(getUnicodeNonBmpRegExp(), '')
.replace(getSupplementaryPrivateUseRegExp(), '')
.replace(getCategoryFormatRegExp(), '');
}
if (punctuations) {
str = str.replace(getPunctuationRegExp(), '');
Expand Down
12 changes: 12 additions & 0 deletions lib/commons/text/unicode.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,3 +83,15 @@ export function getSupplementaryPrivateUseRegExp() {
// ┏━━━━━━┻━━━━━━┓┏━━━━━━┻━━━━━━┓
return /[\uDB80-\uDBBF][\uDC00-\uDFFF]/g;
}

/**
* Get regular expression for unicode format category.
* When we drop IE11 we can instead use unicode character escape `/p{Cf}/gu`
* Reference:
* - https://www.compart.com/en/unicode/category/Cf
*
* @returns {RegExp}
*/
export function getCategoryFormatRegExp() {
return /[\xAD\u0600-\u0605\u061C\u06DD\u070F\u08E2\u180E\u200B-\u200F\u202A-\u202E\u2060-\u2064\u2066-\u206F\uFEFF\uFFF9-\uFFFB]|\uD804[\uDCBD\uDCCD]|\uD80D[\uDC30-\uDC38]|\uD82F[\uDCA0-\uDCA3]|\uD834[\uDD73-\uDD7A]|\uDB40[\uDC01\uDC20-\uDC7F]/g;
}